Initial commit: InkFlow — EPUB vers livre audio local (MLX/Kokoro)

backend/inkflow/models.py

@@ -0,0 +1,176 @@
+"""Schemas de donnees partages dans tout le pipeline (pydantic v2).
+
+Ces modeles sont serialises en JSON sur disque (book.json, analysis/chNN.json,
+cast.json, pronunciation.json) et constituent le contrat entre les etapes du
+pipeline. Chaque etape lit l'artefact de la precedente et ecrit le sien.
+"""
+from __future__ import annotations
+
+from enum import Enum
+from typing import Optional
+
+from pydantic import BaseModel, Field
+
+
+class ChapterKind(str, Enum):
+    FRONT = "front"      # couverture, page de titre, mentions editeur (non lu)
+    CHAPTER = "chapter"  # prologue, chapitres numerotes, epilogue (lu)
+    BACK = "back"        # remerciements, glossaire... (lu si texte significatif)
+
+
+class Chapter(BaseModel):
+    index: int                       # ordre dans le spine (0-based)
+    item_id: str                     # idref du manifest opf
+    src: str                         # chemin interne xhtml
+    title: str                       # titre toc brut, ex "1 - ELVI"
+    kind: ChapterKind
+    render: bool                     # doit-on synthetiser l'audio ?
+    number: Optional[str] = None     # "1", "PROLOGUE", "EPILOGUE"...
+    pov: Optional[str] = None        # personnage point de vue, ex "ELVI"
+    word_count: int = 0
+    text_file: Optional[str] = None  # chemin relatif du json de texte (chapters/chNN.json)
+    output_name: Optional[str] = None  # nom du mp3 final, ex "02-Chapitre 1.mp3"
+
+
+class Book(BaseModel):
+    slug: str                        # identifiant interne (dossier data)
+    title: str
+    author: Optional[str] = None
+    language: str = "fr"
+    description: Optional[str] = None
+    cover_file: Optional[str] = None  # chemin du cover extrait dans data/<slug>/
+    chapters: list[Chapter] = Field(default_factory=list)
+
+    @property
+    def render_chapters(self) -> list[Chapter]:
+        return [c for c in self.chapters if c.render]
+
+
+class ChapterText(BaseModel):
+    """Texte brut normalise d'un chapitre (sortie du parser)."""
+    index: int
+    title: str
+    paragraphs: list[str] = Field(default_factory=list)
+
+    @property
+    def word_count(self) -> int:
+        return sum(len(p.split()) for p in self.paragraphs)
+
+
+# --- Analyse (etape Gemma) ---------------------------------------------------
+
+class SegmentType(str, Enum):
+    NARRATION = "narration"
+    DIALOGUE = "dialogue"
+
+
+class Incise(BaseModel):
+    """Borne d'une incise de narration inseree dans une replique de dialogue.
+
+    Offsets (caracteres) dans `Segment.text` : la sous-chaine `text[start:end]`
+    est de la narration (ex: "dit-il", "lanca Drummer") a porter par la voix du
+    narrateur au rendu, sans fragmenter la replique persistee.
+    """
+    start: int   # offset inclus
+    end: int     # offset exclu
+
+
+class Segment(BaseModel):
+    """Unite de synthese : un bout de texte attribue a un locuteur."""
+    type: SegmentType
+    text: str
+    speaker: str = "narrateur"       # "narrateur" ou nom de personnage
+    glued_to_prev: bool = False      # sous-segment issu du meme paragraphe (incise)
+                                     # -> gap audio reduit avec le segment precedent
+    incises: list[Incise] = Field(default_factory=list)  # spans narrateur DANS text
+
+
+class ChapterAnalysis(BaseModel):
+    index: int
+    title: str
+    segments: list[Segment] = Field(default_factory=list)
+
+
+class Character(BaseModel):
+    name: str                        # nom canonique
+    aliases: list[str] = Field(default_factory=list)
+    gender: Optional[str] = None     # "male" | "female" | "unknown"
+    age: Optional[str] = None        # "child" | "young" | "adult" | "old"
+    description: Optional[str] = None
+    voice_id: Optional[str] = None   # id dans la voicebank (assigne au casting)
+
+
+class Cast(BaseModel):
+    narrator_voice_id: Optional[str] = None
+    characters: list[Character] = Field(default_factory=list)
+
+
+class VoiceEntry(BaseModel):
+    """Une voix de la banque, agnostique du moteur.
+
+    `kokoro_voice` est l'identite (rendu Kokoro direct + clip de reference) ;
+    `ref_audio`/`ref_text` servent au clonage Qwen3 (rendu final).
+    """
+    id: str                          # ex "fr_f_siwis"
+    kokoro_voice: str                # ex "ff_siwis"
+    gender: str = "unknown"          # male | female | unknown
+    age: str = "adult"              # child | young | adult | old
+    lang: str = "fr"
+    label: Optional[str] = None      # libelle lisible
+    ref_audio: Optional[str] = None  # chemin du clip (relatif a voicebank/)
+    ref_text: Optional[str] = None   # transcription du clip
+
+
+class Voicebank(BaseModel):
+    entries: list[VoiceEntry] = Field(default_factory=list)
+
+    def by_id(self, voice_id: str) -> Optional[VoiceEntry]:
+        return next((e for e in self.entries if e.id == voice_id), None)
+
+    def by_gender(self, gender: str) -> list[VoiceEntry]:
+        return [e for e in self.entries if e.gender == gender]
+
+
+class PronunciationEntry(BaseModel):
+    term: str                        # graphie d'origine, ex "Tiamat"
+    replacement: str                 # graphie phonetique guidee, ex "Tia-mat"
+    note: Optional[str] = None
+    enabled: bool = True
+
+
+class Pronunciation(BaseModel):
+    entries: list[PronunciationEntry] = Field(default_factory=list)
+
+
+# --- Etat du projet (orchestration / UI) ------------------------------------
+
+class StageStatus(str, Enum):
+    PENDING = "pending"
+    RUNNING = "running"
+    DONE = "done"
+    ERROR = "error"
+
+
+class ChapterRenderState(BaseModel):
+    index: int
+    status: StageStatus = StageStatus.PENDING
+    progress: float = 0.0            # 0..1
+    mp3: Optional[str] = None        # nom du fichier de sortie
+    backend: Optional[str] = None
+    error: Optional[str] = None
+
+
+class ProjectState(BaseModel):
+    """Etat persistant d'un livre, pilote par l'orchestrateur et lu par l'UI."""
+    slug: str
+    title: str
+    stages: dict[str, StageStatus] = Field(default_factory=dict)  # parse/analyze/cast/pronounce
+    analyzed_chapters: list[int] = Field(default_factory=list)
+    render: dict[int, ChapterRenderState] = Field(default_factory=dict)
+    # Job courant (pour l'affichage temps reel).
+    active_stage: Optional[str] = None
+    active_detail: Optional[str] = None
+    active_progress: float = 0.0
+
+    def stage(self, name: str) -> StageStatus:
+        return self.stages.get(name, StageStatus.PENDING)